{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4984384759525295,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12492192379762648,
      "grad_norm": 0.27754032611846924,
      "learning_rate": 2e-05,
      "loss": 0.1442,
      "step": 100
    },
    {
      "epoch": 0.24984384759525297,
      "grad_norm": 0.2751781642436981,
      "learning_rate": 2e-05,
      "loss": 0.088,
      "step": 200
    },
    {
      "epoch": 0.3747657713928795,
      "grad_norm": 0.23674216866493225,
      "learning_rate": 2e-05,
      "loss": 0.0738,
      "step": 300
    },
    {
      "epoch": 0.49968769519050593,
      "grad_norm": 0.23040202260017395,
      "learning_rate": 2e-05,
      "loss": 0.0643,
      "step": 400
    },
    {
      "epoch": 0.6246096189881324,
      "grad_norm": 0.26208606362342834,
      "learning_rate": 2e-05,
      "loss": 0.0584,
      "step": 500
    },
    {
      "epoch": 0.749531542785759,
      "grad_norm": 0.2172231376171112,
      "learning_rate": 2e-05,
      "loss": 0.0534,
      "step": 600
    },
    {
      "epoch": 0.8744534665833854,
      "grad_norm": 0.21661953628063202,
      "learning_rate": 2e-05,
      "loss": 0.0502,
      "step": 700
    },
    {
      "epoch": 0.9993753903810119,
      "grad_norm": 0.186213880777359,
      "learning_rate": 2e-05,
      "loss": 0.0471,
      "step": 800
    },
    {
      "epoch": 1.1242973141786383,
      "grad_norm": 0.2086647003889084,
      "learning_rate": 2e-05,
      "loss": 0.0373,
      "step": 900
    },
    {
      "epoch": 1.2492192379762648,
      "grad_norm": 0.1900208592414856,
      "learning_rate": 2e-05,
      "loss": 0.0351,
      "step": 1000
    },
    {
      "epoch": 1.3741411617738915,
      "grad_norm": 0.21206732094287872,
      "learning_rate": 2e-05,
      "loss": 0.0349,
      "step": 1100
    },
    {
      "epoch": 1.499063085571518,
      "grad_norm": 0.20564615726470947,
      "learning_rate": 2e-05,
      "loss": 0.0332,
      "step": 1200
    },
    {
      "epoch": 1.6239850093691444,
      "grad_norm": 0.2596442997455597,
      "learning_rate": 2e-05,
      "loss": 0.0313,
      "step": 1300
    },
    {
      "epoch": 1.7489069331667708,
      "grad_norm": 0.18866442143917084,
      "learning_rate": 2e-05,
      "loss": 0.0309,
      "step": 1400
    },
    {
      "epoch": 1.8738288569643973,
      "grad_norm": 0.19815115630626678,
      "learning_rate": 2e-05,
      "loss": 0.0298,
      "step": 1500
    },
    {
      "epoch": 1.9987507807620237,
      "grad_norm": 0.21096043288707733,
      "learning_rate": 2e-05,
      "loss": 0.0281,
      "step": 1600
    },
    {
      "epoch": 2.12367270455965,
      "grad_norm": 0.1663718819618225,
      "learning_rate": 2e-05,
      "loss": 0.0191,
      "step": 1700
    },
    {
      "epoch": 2.2485946283572766,
      "grad_norm": 0.1737908571958542,
      "learning_rate": 2e-05,
      "loss": 0.0191,
      "step": 1800
    },
    {
      "epoch": 2.373516552154903,
      "grad_norm": 0.21257372200489044,
      "learning_rate": 2e-05,
      "loss": 0.0191,
      "step": 1900
    },
    {
      "epoch": 2.4984384759525295,
      "grad_norm": 0.21343937516212463,
      "learning_rate": 2e-05,
      "loss": 0.0185,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 2400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 94237318184960.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}